An improved similarity-based prognostic algorithm for RUL estimation using an RNN autoencoder scheme

Yu, Wennian; Kim, Il Yong; Mechefske, Chris K.

doi:10.1016/j.ress.2020.106926

Cited by 184 publications

(54 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the similarity between the reliability indices can be calculated by (6),

where

is the relaxing parameter, which is set as

in this paper [ 56 ]. For a specific matching between the unit i in the training set and the unit j in the test set, the RUL of the test unit j based on the training set i when considering that the time lag

is calculated by (7),

where the

is the length of the reliability indices of the run-to-failure training set i .…”

Section: Methodsmentioning

confidence: 99%

Real-Time Prognostics of Engineered Systems under Time Varying External Conditions Based on the COX PHM and VARX Hybrid Approach

Zhu

2021

Sensors

View full text Add to dashboard Cite

In spite of the development of the Prognostics and Health Management (PHM) during past decades, the reliability prognostics of engineered systems under time-varying external conditions still remains a challenge in such a field. When considering the challenge mentioned above, a hybrid method for predicting the reliability index and the Remaining Useful Life (RUL) of engineered systems under time-varying external conditions is proposed in this paper. The proposed method is competent in reflecting the influence of time-varying external conditions on the degradation behaviour of engineered systems. Based on a subset of the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset as case studies, the Cox Proportional Hazards Model (Cox PHM) with time-varying covariates is utilised to generate the reliability indices of individual turbofan units. Afterwards, a Vector Autoregressive model with Exogenous variables (VARX) combined with pairwise Conditional Granger Causality (CGC) tests for sensor selections is defined to model the time-varying influence of sensor signals on the reliability indices of different units that have been previously generated by the Cox PHM with time-varying covariates. During the reliability prediction, the Fourier Grey Model (FGM) is employed with the time series models for long-term forecasting of the external conditions. The results show that the method that is proposed in this paper is competent for the RUL prediction as compared with baseline approaches.

show abstract

“…Furthermore, the similarity between the reliability indices can be calculated by (6),

where

is the relaxing parameter, which is set as

is calculated by (7),

where the

is the length of the reliability indices of the run-to-failure training set i .…”

Section: Methodsmentioning

confidence: 99%

Real-Time Prognostics of Engineered Systems under Time Varying External Conditions Based on the COX PHM and VARX Hybrid Approach

Zhu

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Bayesian model [204][205][206] State space model [118,207,208] Filter model [209- [189,190,192] Auto-encoder [191] Filter model [193]…”

Section: Gamma Processmentioning

confidence: 99%

“…Based on the previous research foundation, Xiang et al [190] proposed LSTMP-A, which is more accurate in predicting the RUL of gear. Kim and coauthors [191] based on the automatic coding of bidirectional RNN, and a method for estimating RUL of mechanical systems was proposed.…”

Section: Dtmentioning

confidence: 99%

Digital Twin-Driven Remaining Useful Life Prediction for Gear Performance Degradation: A Review

Liu

Dong

2021

Journal of Computing and Information Science in Engineering

View full text Add to dashboard Cite

As a transmission component, the gear has been obtained widespread attention. The remaining useful life (RUL) prediction of gear is critical to the prognostics health management (PHM) of gear transmission systems. The digital twin (DT) provides support for gear RUL prediction with the advantages of rich health information data and accurate health indicators (HI). This paper reviews digital twin-driven RUL prediction methods for gear performance degradation, from the view of digital twin-driven physical model-based and virtual model-based prediction method. From the view of physical model-based one, it includes prediction model based on gear crack, gear fatigue, gear surface scratch, gear tooth breakage, and gear permanent deformation. From the view of digital twin-driven virtual model-based one, it includes non-deep learning methods, and deep learning methods. Non-deep learning methods include wiener process, gamma process, hidden Markov model (HMM), regression-based model, proportional hazard model. Deep learning methods include deep neural networks (DNN), deep belief networks (DBN), convolutional neural networks (CNN), and recurrent neural networks (RNN), etc. It mainly summarizes the performance degradation and life test of various models in gear, and evaluates the advantages and disadvantages of various methods. In addition, it encourages future works.

show abstract

“…It can not only process sequence data but also extract features well. Furthermore, RNNs have been used in the field of RUL prediction ( Yu, Kim & Mechefske, 2020 ; Guo et al, 2017 ). However, such networks cannot deal with the weight explosion and gradient disappearance problems caused by recursion.…”

Section: Literature Reviewmentioning

confidence: 99%

Data-driven remaining useful life prediction based on domain adaptation

Wen

Xiao

Wang

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

As an important part of prognostics and health management, remaining useful life (RUL) prediction can provide users and managers with system life information and improve the reliability of maintenance systems. Data-driven methods are powerful tools for RUL prediction because of their great modeling abilities. However, most current data-driven studies require large amounts of labeled training data and assume that the training data and test data follow similar distributions. In fact, the collected data are often variable due to different equipment operating conditions, fault modes, and noise distributions. As a result, the assumption that the training data and the test data obey the same distribution may not be valid. In response to the above problems, this paper proposes a data-driven framework with domain adaptability using a bidirectional gated recurrent unit (BGRU). The framework uses a domain-adversarial neural network (DANN) to implement transfer learning (TL) from the source domain to the target domain, which contains only sensor information. To verify the effectiveness of the proposed method, we analyze the IEEE PHM 2012 Challenge datasets and use them for verification. The experimental results show that the generalization ability of the model is effectively improved through the domain adaptation approach.

show abstract

An improved similarity-based prognostic algorithm for RUL estimation using an RNN autoencoder scheme

Cited by 184 publications

References 21 publications

Real-Time Prognostics of Engineered Systems under Time Varying External Conditions Based on the COX PHM and VARX Hybrid Approach

Real-Time Prognostics of Engineered Systems under Time Varying External Conditions Based on the COX PHM and VARX Hybrid Approach

Digital Twin-Driven Remaining Useful Life Prediction for Gear Performance Degradation: A Review

Data-driven remaining useful life prediction based on domain adaptation

Contact Info

Product

Resources

About